completion_create_params
Classes:
Name | Description |
---|---|
CompletionCreateParamsBase |
|
CompletionCreateParamsNonStreaming |
|
CompletionCreateParamsStreaming |
|
Attributes:
Name | Type | Description |
---|---|---|
CompletionCreateParams |
|
CompletionCreateParams
module-attribute
CompletionCreateParams = Union[
CompletionCreateParamsNonStreaming,
CompletionCreateParamsStreaming,
]
CompletionCreateParamsBase
Attributes:
Name | Type | Description |
---|---|---|
best_of |
Optional[int]
|
Generates |
echo |
Optional[bool]
|
Echo back the prompt in addition to the completion |
frequency_penalty |
Optional[float]
|
Number between -2.0 and 2.0. |
logit_bias |
Optional[Dict[str, int]]
|
Modify the likelihood of specified tokens appearing in the completion. |
logprobs |
Optional[int]
|
Include the log probabilities on the |
max_tokens |
Optional[int]
|
The maximum number of tokens that can be generated in the |
model |
Required[Union[str, Literal['gpt-3.5-turbo-instruct', 'davinci-002', 'babbage-002']]]
|
ID of the model to use. |
n |
Optional[int]
|
How many completions to generate for each prompt. |
presence_penalty |
Optional[float]
|
Number between -2.0 and 2.0. |
prompt |
Required[Union[str, List[str], Iterable[int], Iterable[Iterable[int]], None]]
|
The prompt(s) to generate completions for, encoded as a string, array of |
seed |
Optional[int]
|
If specified, our system will make a best effort to sample deterministically, |
stop |
Union[Optional[str], List[str], None]
|
Up to 4 sequences where the API will stop generating further tokens. |
suffix |
Optional[str]
|
The suffix that comes after a completion of inserted text. |
temperature |
Optional[float]
|
What sampling temperature to use, between 0 and 2. |
top_p |
Optional[float]
|
An alternative to sampling with temperature, called nucleus sampling, where the |
user |
str
|
A unique identifier representing your end-user, which can help OpenAI to monitor |
best_of
instance-attribute
Generates best_of
completions server-side and returns the "best" (the one with
the highest log probability per token). Results cannot be streamed.
When used with n
, best_of
controls the number of candidate completions and
n
specifies how many to return – best_of
must be greater than n
.
Note: Because this parameter generates many completions, it can quickly
consume your token quota. Use carefully and ensure that you have reasonable
settings for max_tokens
and stop
.
frequency_penalty
instance-attribute
Number between -2.0 and 2.0.
Positive values penalize new tokens based on their existing frequency in the text so far, decreasing the model's likelihood to repeat the same line verbatim.
See more information about frequency and presence penalties.
logit_bias
instance-attribute
Modify the likelihood of specified tokens appearing in the completion.
Accepts a JSON object that maps tokens (specified by their token ID in the GPT tokenizer) to an associated bias value from -100 to 100. You can use this tokenizer tool to convert text to token IDs. Mathematically, the bias is added to the logits generated by the model prior to sampling. The exact effect will vary per model, but values between -1 and 1 should decrease or increase likelihood of selection; values like -100 or 100 should result in a ban or exclusive selection of the relevant token.
As an example, you can pass {"50256": -100}
to prevent the <|endoftext|> token
from being generated.
logprobs
instance-attribute
Include the log probabilities on the logprobs
most likely output tokens, as
well the chosen tokens. For example, if logprobs
is 5, the API will return a
list of the 5 most likely tokens. The API will always return the logprob
of
the sampled token, so there may be up to logprobs+1
elements in the response.
The maximum value for logprobs
is 5.
max_tokens
instance-attribute
The maximum number of tokens that can be generated in the completion.
The token count of your prompt plus max_tokens
cannot exceed the model's
context length.
Example Python code
for counting tokens.
model
instance-attribute
model: Required[
Union[
str,
Literal[
"gpt-3.5-turbo-instruct",
"davinci-002",
"babbage-002",
],
]
]
ID of the model to use.
You can use the List models API to see all of your available models, or see our Model overview for descriptions of them.
n
instance-attribute
How many completions to generate for each prompt.
Note: Because this parameter generates many completions, it can quickly
consume your token quota. Use carefully and ensure that you have reasonable
settings for max_tokens
and stop
.
presence_penalty
instance-attribute
Number between -2.0 and 2.0.
Positive values penalize new tokens based on whether they appear in the text so far, increasing the model's likelihood to talk about new topics.
See more information about frequency and presence penalties.
prompt
instance-attribute
The prompt(s) to generate completions for, encoded as a string, array of strings, array of tokens, or array of token arrays.
Note that <|endoftext|> is the document separator that the model sees during training, so if a prompt is not specified the model will generate as if from the beginning of a new document.
seed
instance-attribute
If specified, our system will make a best effort to sample deterministically,
such that repeated requests with the same seed
and parameters should return
the same result.
Determinism is not guaranteed, and you should refer to the system_fingerprint
response parameter to monitor changes in the backend.
stop
instance-attribute
Up to 4 sequences where the API will stop generating further tokens.
The returned text will not contain the stop sequence.
suffix
instance-attribute
The suffix that comes after a completion of inserted text.
This parameter is only supported for gpt-3.5-turbo-instruct
.
temperature
instance-attribute
What sampling temperature to use, between 0 and 2.
Higher values like 0.8 will make the output more random, while lower values like 0.2 will make it more focused and deterministic.
We generally recommend altering this or top_p
but not both.
top_p
instance-attribute
An alternative to sampling with temperature, called nucleus sampling, where the model considers the results of the tokens with top_p probability mass. So 0.1 means only the tokens comprising the top 10% probability mass are considered.
We generally recommend altering this or temperature
but not both.
user
instance-attribute
user: str
A unique identifier representing your end-user, which can help OpenAI to monitor and detect abuse. Learn more.
CompletionCreateParamsNonStreaming
Attributes:
Name | Type | Description |
---|---|---|
stream |
Optional[Literal[False]]
|
Whether to stream back partial progress. |
stream
instance-attribute
stream: Optional[Literal[False]]
Whether to stream back partial progress.
If set, tokens will be sent as data-only
server-sent events
as they become available, with the stream terminated by a data: [DONE]
message.
Example Python code.
CompletionCreateParamsStreaming
Attributes:
Name | Type | Description |
---|---|---|
stream |
Required[Literal[True]]
|
Whether to stream back partial progress. |
stream
instance-attribute
Whether to stream back partial progress.
If set, tokens will be sent as data-only
server-sent events
as they become available, with the stream terminated by a data: [DONE]
message.
Example Python code.